Open AccessPosted Content
OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
Reads0
Chats0
TLDR
OpenPose is released, the first open-source realtime system for multi-person 2D pose detection, including body, foot, hand, and facial keypoints, and the first combined body and foot keypoint detector, based on an internal annotated foot dataset.Abstract:
Realtime multi-person 2D pose estimation is a key component in enabling machines to have an understanding of people in images and videos. In this work, we present a realtime approach to detect the 2D pose of multiple people in an image. The proposed method uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image. This bottom-up system achieves high accuracy and realtime performance, regardless of the number of people in the image. In previous work, PAFs and body part location estimation were refined simultaneously across training stages. We demonstrate that a PAF-only refinement rather than both PAF and body part location refinement results in a substantial increase in both runtime performance and accuracy. We also present the first combined body and foot keypoint detector, based on an internal annotated foot dataset that we have publicly released. We show that the combined detector not only reduces the inference time compared to running them sequentially, but also maintains the accuracy of each component individually. This work has culminated in the release of OpenPose, the first open-source realtime system for multi-person 2D pose detection, including body, foot, hand, and facial keypoints.read more
Citations
More filters
Posted Content
When Healthcare Meets Off-the-Shelf WiFi: A Non-Wearable and Low-Costs Approach for In-Home Monitoring
TL;DR: Off-the-shelf WiFi devices are capable of capturing fine-grained human pose figures, similar to cameras, even through a wall and track accurate respiration status, thus demonstrating the effectiveness and feasibility of the approach for in-home monitoring.
Proceedings ArticleDOI
Activity-driven Weakly-Supervised Spatio-Temporal Grounding from Untrimmed Videos
Junwen Chen,Wentao Bao,Yu Kong +2 more
TL;DR: This paper proposes a novel spatio-temporal multiple instance learning framework for untrimmed video grounding, which outperforms state-of-the-art methods on YouCookII and RoboWatch datasets.
Automated Lifelog Moment Retrieval based on Image Segmentation and Similarity Scores.
TL;DR: This paper used word vectors to calculate similarity scores between queries and images and used tree boosting as a predictive approach to extract important moments and reduce the image amount for the ImageCLEFlifelog LMRT task.
Journal ArticleDOI
Low-cost Scalable People Tracking System for Human-Robot Collaboration in Industrial Environment
TL;DR: In this article, the use of a people tracking algorithm is proposed to monitor people moving around a robot manipulator and recognize when a person is too close to the robot while performing a task.
Journal ArticleDOI
STAM-CCF: Suspicious Tracking Across Multiple Camera Based on Correlation Filters
TL;DR: STAM-CCF adjusts human identification and prevents errors caused by information loss in case of object occlusion and overlapping for within-camera tracking cases and introduces a camera correlation model and a two-stage gait recognition strategy to deal with problems of re-identification across multiple cameras.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Book ChapterDOI
Microsoft COCO: Common Objects in Context
Tsung-Yi Lin,Michael Maire,Serge Belongie,James Hays,Pietro Perona,Deva Ramanan,Piotr Dollár,C. Lawrence Zitnick +7 more
TL;DR: A new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding by gathering images of complex everyday scenes containing common objects in their natural context.
Proceedings ArticleDOI
Densely Connected Convolutional Networks
TL;DR: DenseNet as mentioned in this paper proposes to connect each layer to every other layer in a feed-forward fashion, which can alleviate the vanishing gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.